Skip to content

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

1.8 KB
Raw Blame

Roadmap

This page describes the current main branch and future directions, without committing to release dates or priorities. For packaged versions, check release notes.

Implemented on main

  • Context and retrieval: L0/L1/L2 context layers, Viking URIs, semantic search, and context-aware retrieval. Concepts
  • Resources: document, code, web, and media imports; scheduled refreshes for re-readable sources. Audio/video files can be stored; understanding requires an enabled, compatible VLM. Resources
  • Updates and history: freshness-aware parent-summary refreshes and Git-backed snapshot commit, history, and restore. Parent refreshes can be deferred; snapshots require explicit commits and restore file content, not historical ACLs or vector indexes. Context layers · Snapshots
  • Sessions and memory: conversation tracking, memory extraction, and session archival. Sessions
  • Access and integration: HTTP API, SDKs, CLI, MCP, and agent plugins. API overview · MCP guide
  • Operations: JSON configuration (ov.conf), multiple model providers, tenant isolation, encryption, observability, and local/S3 storage. Configuration · Deployment

Future directions

  • Further distributed-storage development.
  • More agent-framework adapters.

Track proposals and discuss scope in GitHub issues. To contribute, see the contribution guide.